提示词锚定的视觉-文本蒸馏用于终身行人重识别
Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification
将预训练视觉-语言模型中冻结的文本编码器作为跨域语义锚点，通过提示词蒸馏与自适应提示池实现无样本回放的终身行人重识别，为视觉领域的持续学习提供了一种利用辅助模态稳定语义的通用思路。
原文依据 We observe that the frozen text encoder in pretrained vision-language models can serve as a stable semantic anchor across domains.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论终身行人重识别（LReID）旨在利用顺序收集的数据训练一个具有泛化能力的模型。然而，随着新域的出现，此类模型常遭受语义漂移、适应性受限和灾难性遗忘的困扰。现有的无样本回放方法主要依赖纯视觉蒸馏或参数正则化，而忽视了辅助模态（如文本）在保持语义稳定性和实现增量可塑性方面的潜力。我们观察到，预训练视觉-语言模型中冻结的文本编码器可以作为跨域的稳定语义锚点。为了解耦视觉与文本的角色，我们提出了提示词锚定的视觉-文本蒸馏（PAD），这是一个用于语义对齐和跨域泛化的非对称视觉-文本框架。在文本侧，我们蒸馏提示词以在固定语义空间下保持视觉-文本对齐，使其作为全局语义参考而非主导学习信号。在视觉侧，一个带有自适应提示池的EMA教师通过分配新槽位并冻结旧槽位来实现逐域适应。大量实验表明，PAD在已见和未见域上均显著优于最优方法，在稳定性和可塑性之间实现了强有力的平衡。项目页面：https://github.com/zu-zi/PAD。
英文原文摘要 1361 字符
Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data. However, such models often suffer from semantic drift, limited adaptability, and catastrophic forgetting as new domains emerge. Existing exemplar-free approaches largely rely on visual-only distillation or parameter regularization, while overlooking the potential of auxiliary modalities, such as text, to preserve semantic stability and enable incremental plasticity. We observe that the frozen text encoder in pretrained vision-language models can serve as a stable semantic anchor across domains. To decouple the roles of vision and text, we propose Prompt-Anchored vision-text Distillation (PAD), an asymmetric vision-text framework for semantic alignment and cross-domain generalization. On the textual side, we distill prompts to preserve vision-text alignment under a fixed semantic space, acting as a global semantic reference rather than a dominant learning signal. On the visual side, an EMA-based teacher with an adaptive prompt pool enables domain-wise adaptation by allocating new slots while freezing past ones. Extensive experiments show that PAD substantially outperforms state-of-the-art methods across seen and unseen domains, achieving a strong balance between stability and plasticity. Project page: https://github.com/zu-zi/PAD.